| 基于人工神经网络的手写数字识别 |
| |
| 引用本文： | 付庆玲,韩力群. 基于人工神经网络的手写数字识别[J]. 北京工商大学学报(自然科学版), 2004, 22(3): 43-45 |
| |
| 作者姓名： | 付庆玲 韩力群 |
| |
| 作者单位： | 北京工商大学,信息工程学院,北京,100037 |
| |
| 摘 要： | 基于手写体数字的几何结构提取端点及其方向、凸点及其方向、三叉点数和四叉点数等数字特征值,运用单字单网的10个并行BP神经网络进行数字识别,达到很好的识别效果.
|
| 关 键 词： | 数字识别 特征向量 多层BP网 |
| 文章编号： | 1671-1513(2004)03-0043-03 |
| 修稿时间： | 2004-02-09 |
RECOGNITION FOR HANDWRITTEN NUMBERS BASED ON ARTIFICAL NEURON NETWORK |
| |
| FU Qing-ling,HAN Li-qun. RECOGNITION FOR HANDWRITTEN NUMBERS BASED ON ARTIFICAL NEURON NETWORK[J]. Journal of Beijing Technology and Business University:Natural Science Edition, 2004, 22(3): 43-45 |
| |
| Authors: | FU Qing-ling HAN Li-qun |
| |
| Abstract: | Network inputting character is a better method at present. This paper based on free handwritten numbers' geometric structure puts forward a way about picking up numbers' eigenvalue for end and its' direction, protruding point and its' direction, three cross point number, four cross point number and so on, and recognizes number which exerts ten paratactic BP neuron network for single number and single network, therefore it obtains better effect. |
| |
| Keywords: | numbers recognition character vectors multilayer BP network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
